© 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. 44921
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Radius
    -0.08
    _radius
    -0.08
     lohnt
    -0.08
    .radius
    -0.08
     halka
    -0.08
    öffnung
    -0.08
    ಜ
    -0.08
    ಾನೆ
    -0.08
     belə
    -0.07
    (radius
    -0.07
    POSITIVE LOGITS
     predomin
    0.09
     obligatorio
    0.09
     oblig
    0.09
     ultimately
    0.08
    olitical
    0.08
     synthes
    0.08
     السف
    0.08
    Requirement
    0.08
     обяз
    0.07
    のみ
    0.07
    Activations Density 0.008%

    No Known Activations