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. 106133
    Prev
    Next
    INDEX
    Explanations

    invitations to stay

    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
     XOR
    -0.08
     ис
    -0.08
     �
    -0.08
     ô
    -0.07
     PC
    -0.07
    iza
    -0.07
     exploit
    -0.07
     whe
    -0.07
     AND
    -0.07
     PCR
    -0.07
    POSITIVE LOGITS
     trú
    0.11
    多久
    0.11
     linger
    0.11
     lâu
    0.11
     residence
    0.10
     awhile
    0.10
    Forever
    0.10
    Residence
    0.10
    住
    0.10
     müdd
    0.10
    Activations Density 0.055%

    No Known Activations