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. 44191
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ,
    -0.08
     wiping
    -0.08
     and
    -0.07
     hitting
    -0.07
    /u
    -0.07
    Entering
    -0.07
    (u
    -0.07
     wipe
    -0.07
    sym
    -0.07
    cing
    -0.07
    POSITIVE LOGITS
    Skype
    0.09
    ાચાર
    0.09
     כזה
    0.09
     desse
    0.09
     પોત
    0.09
     Contudo
    0.09
    Publicado
    0.08
    。</
    0.08
     Sprecher
    0.08
    ુખ
    0.08
    Activations Density 0.142%

    No Known Activations