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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 53560
    Prev
    Next
    INDEX
    Explanations

    door

    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
     malaria
    -0.08
     coordin
    -0.07
     Moodle
    -0.07
     expanding
    -0.07
     direta
    -0.07
     קוק
    -0.07
     prophets
    -0.07
     believers
    -0.07
     occupies
    -0.07
    永
    -0.07
    POSITIVE LOGITS
    ittings
    0.08
     frozen
    0.08
     Industrie
    0.08
    actical
    0.08
    TACT
    0.07
    يارات
    0.07
     ventre
    0.07
     műkö
    0.07
     verstel
    0.07
     catt
    0.07
    Activations Density 0.001%

    No Known Activations