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. 58267
    Prev
    Next
    INDEX
    Explanations

    and

    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
     Observable
    -0.08
     cancellations
    -0.08
     nyt
    -0.08
    ?>
    -0.08
     Cancellation
    -0.08
    :bg
    -0.08
     Harr
    -0.08
    Observable
    -0.08
    :Register
    -0.07
    arbeiter
    -0.07
    POSITIVE LOGITS
     com
    0.08
     parte
    0.07
     대학
    0.07
    bos
    0.07
     따
    0.07
     لط
    0.07
     casos
    0.07
     지급
    0.07
     مع
    0.07
     관련
    0.07
    Activations Density 0.404%

    No Known Activations