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. 55768
    Prev
    Next
    INDEX
    Explanations

    PR

    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
    зи
    -0.08
    صورت
    -0.08
     flea
    -0.08
    يغ
    -0.08
     bipolar
    -0.08
     पड़
    -0.08
     lied
    -0.08
     pfl
    -0.07
     lob
    -0.07
     colspan
    -0.07
    POSITIVE LOGITS
     기반
    0.09
     drugs
    0.09
     viral
    0.08
    'in
    0.08
    foundation
    0.08
    ®
    0.08
     Verde
    0.08
    .location
    0.08
     DNA
    0.08
     Amp
    0.07
    Activations Density 0.001%

    No Known Activations