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. 58722
    Prev
    Next
    INDEX
    Explanations

    Banning/Underground

    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
    (Frame
    -0.08
    Jul
    -0.08
    ending
    -0.07
    Saat
    -0.07
     סוג
    -0.07
    金额
    -0.07
    duur
    -0.07
     Volvo
    -0.07
     Tx
    -0.07
     sustent
    -0.07
    POSITIVE LOGITS
     resentment
    0.10
     backlash
    0.10
     unrest
    0.10
     rebellious
    0.09
     rebellion
    0.09
     clandest
    0.09
    -resistant
    0.09
     rebell
    0.09
     напад
    0.09
     inevitably
    0.09
    Activations Density 0.047%

    No Known Activations