© 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. 710
    Prev
    Next
    INDEX
    Explanations

    .drop

    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
    ോദ
    -0.09
     fen
    -0.09
     nut
    -0.08
    ோத
    -0.08
    ountry
    -0.08
     ymp
    -0.08
    -Shop
    -0.08
     ration
    -0.08
    POPULAR
    -0.08
     Schwartz
    -0.07
    POSITIVE LOGITS
    forget
    0.09
    forgettable
    0.08
    Vertices
    0.08
     недостат
    0.08
     forget
    0.08
     memoria
    0.07
    .vertices
    0.07
    _vertices
    0.07
    _axes
    0.07
     outfile
    0.07
    Activations Density 0.002%

    No Known Activations