© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1293
    Prev
    Next
    INDEX
    Explanations

    expletives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     puta
    -0.08
     wok
    -0.08
    ergen
    -0.08
     berg
    -0.08
    ern
    -0.07
    isdigit
    -0.07
    emene
    -0.07
    erne
    -0.07
     hack
    -0.07
    ornar
    -0.07
    POSITIVE LOGITS
     coils
    0.08
    Pens
    0.08
     perf
    0.08
    _perf
    0.08
     Pens
    0.07
     Spar
    0.07
    _DO
    0.07
    .channels
    0.07
     Ministerio
    0.07
     योजन
    0.07
    Activations Density 0.000%

    No Known Activations