© 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. 44911
    Prev
    Next
    INDEX
    Explanations

    API code

    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
     subconscious
    -0.08
     filled
    -0.08
    .Top
    -0.08
     partes
    -0.08
     الحج
    -0.08
     elongated
    -0.08
     ingev
    -0.08
     falsas
    -0.08
    .Command
    -0.08
     brainstorm
    -0.07
    POSITIVE LOGITS
     IERC
    0.12
     ERC
    0.11
     માલ
    0.10
     माल
    0.08
     liquidity
    0.08
    (GL
    0.08
     assays
    0.08
    Decimals
    0.08
     jersey
    0.08
     Ripple
    0.08
    Activations Density 0.003%

    No Known Activations