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. 120145
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    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
     કોઇ
    -0.08
    ड़
    -0.08
    however
    -0.08
    velop
    -0.07
    łych
    -0.07
    asını
    -0.07
    zeń
    -0.07
    ng
    -0.07
    ือ
    -0.07
    asının
    -0.07
    POSITIVE LOGITS
     Paran
    0.09
     Kn
    0.07
     Ket
    0.07
     Jum
    0.07
    ಿಸ್
    0.07
     Top
    0.07
     arsenal
    0.07
     setelah
    0.07
    Options
    0.07
    ಾಲಯ
    0.07
    Activations Density 0.001%

    No Known Activations