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. 26973
    Prev
    Next
    INDEX
    Explanations

    period

    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
     enough
    -0.08
    esser
    -0.07
     physiological
    -0.07
     sen
    -0.07
    _l
    -0.07
     theatrical
    -0.07
     But
    -0.07
    olecular
    -0.07
    _spec
    -0.07
    ifically
    -0.07
    POSITIVE LOGITS
     CLOSED
    0.09
     widened
    0.09
    (Func
    0.08
    Shar
    0.08
    (Font
    0.08
    (Tab
    0.08
    (ERROR
    0.08
     onderscheiden
    0.08
    !”↵
    0.07
     tightened
    0.07
    Activations Density 0.121%

    No Known Activations