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. 23-RESID-POST-AA
    6. 130755
    Prev
    Next
    INDEX
    Explanations

    su

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diss
    -0.09
     upe
    -0.09
     ინდ
    -0.09
    רד
    -0.09
     जीवन
    -0.09
     Diss
    -0.08
     চিন
    -0.08
    jeren
    -0.08
     жыцця
    -0.08
     dissolution
    -0.08
    POSITIVE LOGITS
    (false
    0.08
    Art
    0.07
     false
    0.07
    325
    0.07
    Twe
    0.07
    ant
    0.07
     Tro
    0.07
    preset
    0.07
    Outputs
    0.07
    물
    0.07
    Activations Density 0.000%

    No Known Activations