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. 46937
    Prev
    Next
    INDEX
    Explanations

    true

    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
     تای
    -0.09
    kami
    -0.08
     ()=>{↵
    -0.08
    ուտ
    -0.08
     Studium
    -0.08
     કમ
    -0.08
    'I
    -0.08
    yuas
    -0.08
     kami
    -0.08
    ?↵
    -0.08
    POSITIVE LOGITS
     replay
    0.09
     ribbon
    0.08
     Cathedral
    0.08
    _Class
    0.08
    SSL
    0.08
    SD
    0.08
    :l
    0.07
    ubl
    0.07
     Ribbon
    0.07
    RTC
    0.07
    Activations Density 0.000%

    No Known Activations