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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 111780
    Prev
    Next
    INDEX
    Explanations

    guide

    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
    Kann
    -0.09
     Aman
    -0.08
     asta
    -0.08
    െ
    -0.08
     בכך
    -0.08
     Mao
    -0.08
    eftijd
    -0.08
    且
    -0.08
     bur
    -0.07
     heil
    -0.07
    POSITIVE LOGITS
    vors
    0.08
     vors
    0.08
     contrasted
    0.08
    CB
    0.08
     cuffs
    0.08
     Cock
    0.07
    овы
    0.07
    vider
    0.07
    !!!
    0.07
    posa
    0.07
    Activations Density 0.864%

    No Known Activations