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. 45410
    Prev
    Next
    INDEX
    Explanations

    Type II

    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
     режиме
    -0.07
     Jazz
    -0.07
     મેળવ
    -0.07
    ിട്ടില്ല
    -0.07
     મળ
    -0.07
    ുന്നതിന
    -0.07
     Jeanne
    -0.07
    િત
    -0.07
     vet
    -0.07
     معا
    -0.07
    POSITIVE LOGITS
    plays
    0.09
    things
    0.09
    -sac
    0.08
     asin
    0.08
     functioning
    0.07
     nehmen
    0.07
     mahimong
    0.07
     компен
    0.07
    -large
    0.07
     прибор
    0.07
    Activations Density 0.000%

    No Known Activations