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. 112239
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
     want
    -0.08
    sqrt
    -0.07
     <*>
    -0.07
     interval
    -0.07
     xmin
    -0.07
    min
    -0.07
     inte
    -0.07
     intervals
    -0.07
    Intervals
    -0.07
    undir
    -0.07
    POSITIVE LOGITS
    again
    0.10
     क्यों
    0.09
    Again
    0.09
     inderdaad
    0.08
     indeed
    0.08
    antur
    0.08
     again
    0.08
     שוב
    0.08
     Verified
    0.08
     Superb
    0.08
    Activations Density 0.104%

    No Known Activations