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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 111861
    Prev
    Next
    INDEX
    Explanations

    image

    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
    _DECL
    -0.08
    _MOVE
    -0.07
    Member
    -0.07
    _MEMBER
    -0.07
    decl
    -0.07
    tv
    -0.07
    used
    -0.07
    Rgb
    -0.07
    exchange
    -0.07
     keypad
    -0.07
    POSITIVE LOGITS
     ಪ್ರಮುಖ
    0.09
     majeure
    0.08
     хугаца
    0.08
     ಮುಖ್ಯ
    0.08
    ัต
    0.08
    亿
    0.08
     mínimo
    0.08
     risult
    0.08
    оби
    0.08
     extremadamente
    0.08
    Activations Density 0.001%

    No Known Activations