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. 60436
    Prev
    Next
    INDEX
    Explanations

    programming parameters/flags

    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
     Stil
    -0.08
     normale
    -0.08
     offenses
    -0.08
    adra
    -0.08
     INITIAL
    -0.07
     modus
    -0.07
    're
    -0.07
    ้าที่
    -0.07
     specialty
    -0.07
    কদের
    -0.07
    POSITIVE LOGITS
    Regards
    0.07
    .UTF
    0.07
    кан
    0.07
     fjár
    0.07
    acyj
    0.07
    .gui
    0.07
    ם
    0.07
    Inside
    0.07
    .More
    0.07
    .flip
    0.07
    Activations Density 0.001%

    No Known Activations