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. 111614
    Prev
    Next
    INDEX
    Explanations

    explicit scenarios

    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
    -independent
    -0.07
     prat
    -0.07
    _re
    -0.07
     helemaal
    -0.07
    Vai
    -0.07
    Dow
    -0.07
    Everything
    -0.07
    šanu
    -0.07
    From
    -0.07
    ాల
    -0.07
    POSITIVE LOGITS
    ('$
    0.09
     encouragement
    0.08
     affirmation
    0.08
    ngoing
    0.08
     adjustments
    0.08
     affirm
    0.08
    umbia
    0.08
    -Shirts
    0.08
     прыс
    0.08
     тих
    0.08
    Activations Density 0.000%

    No Known Activations