© 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. 23-RESID-POST-AA
    11. 5957
    Prev
    Next
    INDEX
    Explanations

    mer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stuck
    -0.08
     zdrow
    -0.07
    SPEC
    -0.07
    斯
    -0.07
    מוד
    -0.07
     transitioned
    -0.07
     Puffy
    -0.07
     stickers
    -0.07
     пик
    -0.07
     অনুয
    -0.07
    POSITIVE LOGITS
     Hey
    0.08
     फिर
    0.08
    avila
    0.08
     bilər
    0.08
     teine
    0.08
     sœur
    0.08
    Hey
    0.08
    irar
    0.08
    avljen
    0.08
     τη
    0.08
    Activations Density 0.000%

    No Known Activations