© 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. 78993
    Prev
    Next
    INDEX
    Explanations

    remote assistance

    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
    -anchor
    -0.08
     miscellaneous
    -0.08
    \Collection
    -0.08
     السك
    -0.08
    _SECRET
    -0.08
     eaux
    -0.08
     sugary
    -0.08
    _API
    -0.08
     differently
    -0.08
    _anchor
    -0.08
    POSITIVE LOGITS
     remotely
    0.10
     remote
    0.09
    遠
    0.09
     दूर
    0.09
     Tate
    0.08
     remot
    0.08
    直播
    0.08
    (remote
    0.08
     लाइव
    0.08
    .remote
    0.08
    Activations Density 0.032%

    No Known Activations