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. 11-RESID-POST-AA
    6. 12006
    Prev
    Next
    INDEX
    Explanations

    geometry

    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
    /update
    -0.08
     for
    -0.08
    MV
    -0.07
     thermique
    -0.07
     unplug
    -0.07
    Authorize
    -0.07
     which
    -0.07
    _text
    -0.07
    مح
    -0.07
     محبت
    -0.07
    POSITIVE LOGITS
    .ribbon
    0.08
     tournaments
    0.08
     Blond
    0.08
    otl
    0.08
    )null
    0.08
     Garrett
    0.08
     Naked
    0.08
     extrap
    0.08
     Ing
    0.08
     cred
    0.08
    Activations Density 0.025%

    No Known Activations