© 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. 68268
    Prev
    Next
    INDEX
    Explanations

    Equals sign

    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
    భ
    -0.08
    hren
    -0.08
     ಭ
    -0.08
    理念
    -0.08
     affair
    -0.08
     భ
    -0.08
    enseign
    -0.07
    mandatory
    -0.07
     mandatory
    -0.07
    éh
    -0.07
    POSITIVE LOGITS
     wig
    0.08
     એવા
    0.08
     unk
    0.08
     arising
    0.08
    endoza
    0.08
     transverse
    0.07
     Maj
    0.07
    _MUT
    0.07
     Hair
    0.07
     ZX
    0.07
    Activations Density 0.008%

    No Known Activations