© 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. 75463
    Prev
    Next
    INDEX
    Explanations

    colorings

    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
     Squadron
    -0.08
     Che
    -0.07
     Marbella
    -0.07
     Venezuela
    -0.07
    .Debugger
    -0.07
     Mae
    -0.07
     cuadr
    -0.07
    .Height
    -0.07
     calculation
    -0.07
     kilom
    -0.07
    POSITIVE LOGITS
     colors
    0.10
     palette
    0.10
     použí
    0.09
     Palette
    0.09
    _colors
    0.09
    Palette
    0.09
    colors
    0.09
     përd
    0.08
    .used
    0.08
    至少
    0.08
    Activations Density 0.033%

    No Known Activations