Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 24542
    Prev
    Next
    INDEX
    Explanations

    tables

    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
     verb
    -0.08
     leukemia
    -0.08
    -trained
    -0.07
     credential
    -0.07
    HAHA
    -0.07
    .verbose
    -0.07
    ydın
    -0.07
    .UUID
    -0.07
     mad
    -0.07
     달
    -0.07
    POSITIVE LOGITS
     refeições
    0.10
     anv
    0.09
     थोड़ा
    0.09
    餐
    0.08
     tafel
    0.08
    halts
    0.08
     bott
    0.08
     meja
    0.08
     boarded
    0.08
    อาหาร
    0.08
    Activations Density 0.003%

    No Known Activations