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. 77526
    Prev
    Next
    INDEX
    Explanations

    10

    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
    Abstract
    -0.09
     forb
    -0.08
     Abstract
    -0.08
     swirl
    -0.07
    Awesome
    -0.07
    Event
    -0.07
    Serde
    -0.07
    Plot
    -0.07
     fantasia
    -0.07
     blir
    -0.07
    POSITIVE LOGITS
     Derechos
    0.09
     bienestar
    0.08
     visión
    0.08
    vē
    0.08
    ulnerability
    0.08
     cirugía
    0.08
     trabajador
    0.08
    ugador
    0.08
     хирург
    0.08
     Provided
    0.08
    Activations Density 0.002%

    No Known Activations