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. 45639
    Prev
    Next
    INDEX
    Explanations

    candy

    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
    ئ
    -0.08
     منت
    -0.07
     supports
    -0.07
    _DESC
    -0.07
    _st
    -0.07
     embodied
    -0.07
    exual
    -0.07
    oxia
    -0.07
     رہ
    -0.07
    iencia
    -0.07
    POSITIVE LOGITS
     koordin
    0.08
     алды
    0.08
     Intake
    0.08
    env
    0.08
     mwana
    0.08
     intake
    0.08
     Ariel
    0.08
     МВД
    0.07
     deput
    0.07
     Grab
    0.07
    Activations Density 0.003%

    No Known Activations