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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 58692
    Prev
    Next
    INDEX
    Explanations

    legs and feet

    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
    स्
    -0.08
     voluntary
    -0.07
     juris
    -0.07
    Unt
    -0.07
    .experimental
    -0.07
    ాలని
    -0.07
    jit
    -0.07
     rever
    -0.07
     Vehicle
    -0.07
     الت
    -0.07
    POSITIVE LOGITS
     tripod
    0.09
     Cupid
    0.08
     grips
    0.08
     Grip
    0.08
     Bein
    0.08
     grip
    0.08
     Fulton
    0.08
     bölüm
    0.08
     sturd
    0.08
     Feast
    0.08
    Activations Density 0.002%

    No Known Activations