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

    Neuronpedia

    APICircuit 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. 30583
    Prev
    Next
    INDEX
    Explanations

    pacing

    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
     치료
    -0.08
    Params
    -0.07
    ocon
    -0.07
    (Reg
    -0.07
    oplast
    -0.07
     Cauc
    -0.07
    (and
    -0.07
     Zool
    -0.07
     indique
    -0.07
    osome
    -0.07
    POSITIVE LOGITS
     trolley
    0.09
     seleccionar
    0.09
     expenditure
    0.08
     expend
    0.08
     teimum
    0.08
    иң
    0.08
    _Selected
    0.08
     bijdr
    0.08
     ঘৰ
    0.08
     ntawm
    0.08
    Activations Density 0.006%

    No Known Activations