© 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. 183
    Prev
    Next
    INDEX
    Explanations

    Legal

    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
    xiety
    -0.08
    insula
    -0.08
    izabeth
    -0.08
    estes
    -0.08
     dominant
    -0.08
     groeien
    -0.07
     escape
    -0.07
     Lombardia
    -0.07
     arom
    -0.07
    emakers
    -0.07
    POSITIVE LOGITS
    PEL
    0.09
     unix
    0.09
    CS
    0.08
    坑
    0.08
     físicos
    0.08
     ;-
    0.08
     Hallo
    0.08
    Linux
    0.08
     linux
    0.08
    linux
    0.08
    Activations Density 0.511%

    No Known Activations