© 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. 31120
    Prev
    Next
    INDEX
    Explanations

    definite

    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
     washing
    -0.09
    .link
    -0.08
     solidaridad
    -0.08
     धार्मिक
    -0.08
    Myst
    -0.07
     downloading
    -0.07
     Washing
    -0.07
     długo
    -0.07
     civilization
    -0.07
     politico
    -0.07
    POSITIVE LOGITS
     Hess
    0.12
     Toe
    0.10
     Hamilton
    0.09
     quadratic
    0.09
    Toe
    0.08
    Hamilton
    0.08
     GRE
    0.08
     iff
    0.08
     tuned
    0.08
    .transpose
    0.08
    Activations Density 0.004%

    No Known Activations