© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68239
    Prev
    Next
    INDEX
    Explanations

    Java annotations

    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
     hostile
    -0.08
     být
    -0.08
     hör
    -0.08
     fossil
    -0.07
     volcanic
    -0.07
    石
    -0.07
     refining
    -0.07
     Gunn
    -0.07
     precipitation
    -0.07
     Gibraltar
    -0.07
    POSITIVE LOGITS
     lombok
    0.10
     autogenerated
    0.09
     생
    0.09
    @Getter
    0.08
    elijkse
    0.08
     Retrouvez
    0.08
    lijkse
    0.08
     lomb
    0.08
     Lomb
    0.08
    @Builder
    0.08
    Activations Density 0.002%

    No Known Activations