© 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. 31155
    Prev
    Next
    INDEX
    Explanations

    Matching questions

    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
    ,omitempty
    -0.08
    ultur
    -0.08
    730
    -0.08
    pct
    -0.07
    wstring
    -0.07
    :outline
    -0.07
    .Struct
    -0.07
    vaj
    -0.07
     barriers
    -0.07
     records
    -0.07
    POSITIVE LOGITS
    匹
    0.12
     મેચ
    0.11
     Matching
    0.11
    _MATCH
    0.11
    .match
    0.11
    Matching
    0.11
     matching
    0.11
    Match
    0.11
     मैच
    0.10
     Match
    0.10
    Activations Density 0.025%

    No Known Activations