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. 55891
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
     Rip
    -0.08
     grab
    -0.07
    �
    -0.07
    Rip
    -0.07
    .sd
    -0.07
     estacion
    -0.07
    _rt
    -0.07
    29
    -0.07
     locate
    -0.07
    've
    -0.07
    POSITIVE LOGITS
     amendment
    0.09
     amendments
    0.08
     ஆகிய
    0.08
     supplementation
    0.08
     sanés
    0.08
     לק
    0.08
     lainnya
    0.08
    /am
    0.08
    Accounts
    0.08
    zahlungen
    0.08
    Activations Density 0.751%

    No Known Activations