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. 137
    Prev
    Next
    INDEX
    Explanations

    Tom

    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
    spe
    -0.09
     stuffing
    -0.08
     reduct
    -0.08
     Che
    -0.08
     друг
    -0.07
     woo
    -0.07
     kom
    -0.07
    gener
    -0.07
    तम
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     fo
    0.08
     eis
    0.08
     Polit
    0.08
    서
    0.07
     Lay
    0.07
    ф
    0.07
    chio
    0.07
     ori
    0.07
     már
    0.07
     Punch
    0.07
    Activations Density 0.032%

    No Known Activations