Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 53081
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _APPRO
    -0.08
     إجراء
    -0.08
     Flesh
    -0.08
     flesh
    -0.07
     Pri
    -0.07
    -0.07
     cree
    -0.07
    ienti
    -0.07
     preced
    -0.07
    Convention
    -0.07
    POSITIVE LOGITS
    ーーーー
    0.10
     =================================================================================
    0.10
     COPYRIGHT
    0.09
                                                                                                   
    0.09
     perkembangan
    0.08
     pasted
    0.08
     コピー
    0.08
     ----------------------------------------------------------------------------------------------------------------
    0.08
     �
    0.08
    ーー
    0.08
    Activations Density 0.007%

    No Known Activations