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. 91023
    Prev
    Next
    INDEX
    Explanations

    TypeScript code

    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
     screws
    -0.08
     seeds
    -0.08
    _compare
    -0.07
     gä
    -0.07
     Mala
    -0.07
    _normal
    -0.07
    比较
    -0.07
     produziert
    -0.07
    �
    -0.07
    Seeds
    -0.07
    POSITIVE LOGITS
     Narrow
    0.09
     narrowed
    0.09
    certainty
    0.08
     জানা
    0.08
     Surely
    0.08
     narrowing
    0.08
     নিরাপ
    0.08
     narrower
    0.08
    ூ
    0.08
     terpercaya
    0.08
    Activations Density 0.003%

    No Known Activations