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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 77544
    Prev
    Next
    INDEX
    Explanations

    of

    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
    hov
    -0.10
    jets
    -0.08
     find
    -0.07
     Pinto
    -0.07
     Akk
    -0.07
     hingegen
    -0.07
     fuentes
    -0.07
    ుడ
    -0.07
     Latin
    -0.07
    vonne
    -0.07
    POSITIVE LOGITS
     між
    0.08
    伍
    0.08
     dobu
    0.08
     בין
    0.08
    ICON
    0.08
    AUTHOR
    0.07
    IFICATIONS
    0.07
     między
    0.07
    69
    0.07
     sóc
    0.07
    Activations Density 0.001%

    No Known Activations