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. 60735
    Prev
    Next
    INDEX
    Explanations

    that

    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
     trouvent
    -0.08
    chmod
    -0.08
    entities
    -0.07
    chips
    -0.07
     entities
    -0.07
     જેવી
    -0.07
    রণের
    -0.07
     trouve
    -0.07
    主演
    -0.07
    name
    -0.07
    POSITIVE LOGITS
     kuch
    0.10
     meios
    0.08
     ELE
    0.08
    -eye
    0.08
    Tul
    0.08
    Ele
    0.08
    Ey
    0.08
     Leistungen
    0.08
    Dennis
    0.08
    EZ
    0.08
    Activations Density 0.000%

    No Known Activations