© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44845
    Prev
    Next
    INDEX
    Explanations

    code, math, or mazes

    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
     momentos
    -0.08
    \P
    -0.08
     moments
    -0.08
    ின்
    -0.08
    _all
    -0.08
     Moments
    -0.08
    _disabled
    -0.08
     '\'
    -0.07
     measurements
    -0.07
     momenten
    -0.07
    POSITIVE LOGITS
     internationales
    0.08
     internationaux
    0.08
     ocu
    0.08
     ")[
    0.07
     Reve
    0.07
    iculture
    0.07
    loge
    0.07
     nephew
    0.07
     док
    0.07
     Leaves
    0.07
    Activations Density 0.000%

    No Known Activations