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. 11757
    Prev
    Next
    INDEX
    Explanations

    Job benefits

    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
     واس
    -0.08
     leaked
    -0.07
    _failed
    -0.07
    Result
    -0.07
     misplaced
    -0.07
    _result
    -0.07
    ases
    -0.07
    _str
    -0.07
     verstre
    -0.07
     ढ
    -0.07
    POSITIVE LOGITS
     anual
    0.09
     Freude
    0.08
     callable
    0.08
     ♥
    0.08
     landscaped
    0.08
     condolences
    0.08
     ❤️
    0.08
     freuen
    0.08
     customizable
    0.08
     ○
    0.08
    Activations Density 0.008%

    No Known Activations