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. 113774
    Prev
    Next
    INDEX
    Explanations

    clay

    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
    ikir
    -0.08
    әк
    -0.08
     casually
    -0.08
     Cyr
    -0.08
    қара
    -0.07
     apoyo
    -0.07
    -che
    -0.07
     constructors
    -0.07
     earbuds
    -0.07
    &,
    -0.07
    POSITIVE LOGITS
     refuse
    0.09
     অধিক
    0.08
     құрам
    0.08
     electoral
    0.08
     Electoral
    0.08
     flushing
    0.07
     vill
    0.07
     résist
    0.07
     dies
    0.07
     predicts
    0.07
    Activations Density 0.005%

    No Known Activations