© 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. 11-RESID-POST-AA
    11. 24672
    Prev
    Next
    INDEX
    Explanations

    dropped

    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
    zone
    -0.09
    る
    -0.08
     gast
    -0.08
     zo
    -0.07
     garant
    -0.07
     era
    -0.07
    .tsv
    -0.07
    ゾ
    -0.07
     sociale
    -0.07
    ে
    -0.07
    POSITIVE LOGITS
     perpendicular
    0.09
    Aid
    0.08
     gratuit
    0.08
     Aid
    0.08
     объект
    0.08
     чак
    0.07
     attendants
    0.07
     khusus
    0.07
     chord
    0.07
    _inside
    0.07
    Activations Density 0.007%

    No Known Activations