© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 45406
    Prev
    Next
    INDEX
    Explanations

    code parameters

    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
     basement
    -0.09
    /FM
    -0.08
    OMET
    -0.08
     обз
    -0.07
    usten
    -0.07
     gau
    -0.07
    תח
    -0.07
     బ్య
    -0.07
    (Component
    -0.07
    PEC
    -0.07
    POSITIVE LOGITS
     sustit
    0.09
     substit
    0.09
     substitution
    0.09
     substitutions
    0.09
    Animating
    0.08
     supplying
    0.08
     factual
    0.08
     selbstverständlich
    0.07
     populate
    0.07
    olate
    0.07
    Activations Density 0.003%

    No Known Activations