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. 77321
    Prev
    Next
    INDEX
    Explanations

    difference

    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
     announce
    -0.07
    olk
    -0.07
    cut
    -0.07
     honor
    -0.07
     announcements
    -0.07
    -0.07
     Cut
    -0.07
     announces
    -0.07
     ceremony
    -0.07
    IRI
    -0.07
    POSITIVE LOGITS
    .increment
    0.09
    CREMENT
    0.09
    _increment
    0.09
    .adjust
    0.08
     debounce
    0.08
    Increment
    0.08
     kilometer
    0.08
     охш
    0.08
     decrement
    0.08
    百分点
    0.08
    Activations Density 0.014%

    No Known Activations