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. 109706
    Prev
    Next
    INDEX
    Explanations

    well

    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
     watershed
    -0.09
     Welsh
    -0.08
     gamut
    -0.08
     Cep
    -0.08
     Needed
    -0.08
     Kami
    -0.07
    棚
    -0.07
     Through
    -0.07
     urgently
    -0.07
    苦
    -0.07
    POSITIVE LOGITS
    enc
    0.09
     entice
    0.08
     ||
    0.08
     prey
    0.08
     fel
    0.08
     pork
    0.08
    GF
    0.08
     seasoned
    0.08
     exploiting
    0.08
    金币
    0.08
    Activations Density 0.049%

    No Known Activations