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. 55781
    Prev
    Next
    INDEX
    Explanations

    gate

    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
     shir
    -0.09
     etti
    -0.08
     genomic
    -0.07
     prose
    -0.07
     minuta
    -0.07
     genom
    -0.07
    fulfilled
    -0.07
     logistic
    -0.07
     manga
    -0.07
    -fi
    -0.07
    POSITIVE LOGITS
     Noel
    0.09
    -relative
    0.08
     тиг
    0.08
     tərəfind
    0.08
     Hear
    0.08
     Apex
    0.08
     Poison
    0.08
    νης
    0.08
     вещества
    0.08
     Offre
    0.08
    Activations Density 0.002%

    No Known Activations