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. 65830
    Prev
    Next
    INDEX
    Explanations

    presidential

    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
     filed
    -0.08
     plants
    -0.08
     indexes
    -0.07
    ,error
    -0.07
     следующий
    -0.07
     swap
    -0.07
     Filed
    -0.07
     aka
    -0.07
     vegetarian
    -0.07
     reco
    -0.07
    POSITIVE LOGITS
     Mek
    0.09
     θεραπε
    0.08
    mera
    0.08
    .attrib
    0.07
    azza
    0.07
    mee
    0.07
    inio
    0.07
    ements
    0.07
    ِينَ
    0.07
     മത്സ
    0.07
    Activations Density 0.002%

    No Known Activations