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. 46090
    Prev
    Next
    INDEX
    Explanations

    im

    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
    /social
    -0.09
     optimisation
    -0.08
    bundle
    -0.08
    -status
    -0.08
    surface
    -0.08
    objective
    -0.08
     bundles
    -0.08
    bund
    -0.08
    /date
    -0.08
     SOCIAL
    -0.08
    POSITIVE LOGITS
     бытов
    0.08
     трех
    0.08
    .reactivex
    0.08
     നിയമ
    0.08
     uni
    0.08
     காவ
    0.08
     हम
    0.08
     философ
    0.07
     ру
    0.07
     कैम
    0.07
    Activations Density 0.002%

    No Known Activations