© 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. 19-RESID-POST-AA
    11. 102930
    Prev
    Next
    INDEX
    Explanations

    sweat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    альное
    -0.08
    (size
    -0.08
     execute
    -0.08
    -0.08
    <size
    -0.08
    `
    -0.08
    iseren
    -0.08
    atay
    -0.07
    (ctrl
    -0.07
    аў
    -0.07
    POSITIVE LOGITS
    pants
    0.15
    bands
    0.13
    shirts
    0.11
    iness
    0.11
    mill
    0.10
    shops
    0.10
    shirt
    0.10
    fallen
    0.10
    htaking
    0.10
    shed
    0.10
    Activations Density 0.002%
    No Known Activations