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. 43048
    Prev
    Next
    INDEX
    Explanations

    Expressing negativity or regret

    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
    "></
    -0.07
     careful
    -0.07
    \Security
    -0.07
    >"+
    -0.07
    _customize
    -0.07
    Req
    -0.07
     Guides
    -0.07
    Guid
    -0.07
     vistos
    -0.07
    autions
    -0.07
    POSITIVE LOGITS
    无法
    0.09
     stray
    0.08
     disappoint
    0.08
     uninsured
    0.08
     ухуд
    0.08
     disappointing
    0.08
     oublié
    0.08
     :(↵↵
    0.08
    Unfortunately
    0.08
     desperd
    0.08
    Activations Density 0.117%

    No Known Activations