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. 27451
    Prev
    Next
    INDEX
    Explanations

    -

    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
    汗
    -0.09
     кат
    -0.08
     UNA
    -0.07
    .vol
    -0.07
    .un
    -0.07
     মাধ্যমে
    -0.07
     pases
    -0.07
     stoj
    -0.07
    .complete
    -0.07
    经典
    -0.07
    POSITIVE LOGITS
    zuf
    0.08
    Comparable
    0.08
     biscuits
    0.08
     voorzichtig
    0.08
     કરતા
    0.08
     Comparable
    0.08
    zus
    0.07
    Sql
    0.07
    iseksi
    0.07
     väga
    0.07
    Activations Density 0.014%

    No Known Activations