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. 30379
    Prev
    Next
    INDEX
    Explanations

    Sue and BB cream

    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
     SAY
    -0.08
     તથા
    -0.08
     ואף
    -0.08
     mr
    -0.08
     વેપ
    -0.08
     nawo
    -0.08
     kunye
    -0.08
     વ
    -0.07
     pak
    -0.07
     nore
    -0.07
    POSITIVE LOGITS
     cirugía
    0.08
     bleeding
    0.08
    requent
    0.08
     Kindergarten
    0.08
    _chip
    0.07
    versicherung
    0.07
    ances
    0.07
     chiropractic
    0.07
    <header
    0.07
    істі
    0.07
    Activations Density 0.002%

    No Known Activations