Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 7-RESID-POST-AA
    6. 131052
    Prev
    Next
    INDEX
    Explanations

    k

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jot
    -0.09
     impedance
    -0.09
     Largo
    -0.08
    tray
    -0.08
     Blockly
    -0.08
     shortening
    -0.08
     Liberty
    -0.08
    nbsp
    -0.08
    _void
    -0.08
     Eternal
    -0.08
    POSITIVE LOGITS
     improbable
    0.10
     successes
    0.08
     probabilities
    0.08
    莉
    0.08
     occurring
    0.08
     Lach
    0.07
    0.07
    Retries
    0.07
    ให้
    0.07
     sukces
    0.07
    Activations Density 0.034%

    No Known Activations