Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 9101
    Prev
    Next
    INDEX
    Explanations

    6

    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
    ;margin
    -0.09
    (engine
    -0.08
    _WRITE
    -0.08
    (coords
    -0.08
    _models
    -0.07
    (conv
    -0.07
     Models
    -0.07
     groundwork
    -0.07
    _GREEN
    -0.07
    fl
    -0.07
    POSITIVE LOGITS
     hashtags
    0.09
     carav
    0.09
     الجنسية
    0.08
     filename
    0.08
     berupa
    0.08
     عشر
    0.08
     hashtag
    0.08
     username
    0.08
     sexe
    0.08
    เกมสล็อต
    0.08
    Activations Density 0.004%

    No Known Activations