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. 3-RESID-POST-AA
    6. 12443
    Prev
    Next
    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constructed
    -0.08
     ampl
    -0.08
    _lambda
    -0.07
     Eaton
    -0.07
     firstly
    -0.07
    tick
    -0.07
     gry
    -0.07
    Firewall
    -0.07
     juillet
    -0.07
     #{@
    -0.07
    POSITIVE LOGITS
    .widgets
    0.08
    ఎ
    0.08
    .skill
    0.07
    .flat
    0.07
    foil
    0.07
     సె
    0.07
     Siy
    0.07
    اسي
    0.07
     preciosa
    0.07
     creativo
    0.07
    Activations Density 0.003%

    No Known Activations