© 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. 19-RESID-POST-AA
    11. 102953
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .↵↵
    -0.11
    ..↵↵
    -0.11
     (
    -0.11
    ?↵↵
    -0.10
     (=
    -0.10
     perhaps
    -0.10
     maybe
    -0.09
    ()↵↵
    -0.09
    —which
    -0.09
     sitten
    -0.09
    POSITIVE LOGITS
     there's
    0.16
     There
    0.15
     There's
    0.15
     there
    0.15
     هناك
    0.15
    There's
    0.15
     emphasis
    0.14
    There
    0.14
     reliance
    0.13
     există
    0.13
    Activations Density 0.100%

    No Known Activations