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. 106036
    Prev
    Next
    INDEX
    Explanations

    a

    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
     Caring
    -0.08
    #"
    -0.08
    aule
    -0.07
     Convey
    -0.07
    ropical
    -0.07
     injunction
    -0.07
    日
    -0.07
    рез
    -0.07
     (;;
    -0.07
     reparar
    -0.07
    POSITIVE LOGITS
    ṃ
    0.07
     numbering
    0.07
    াই
    0.07
     flavours
    0.07
    possibly
    0.07
     scoring
    0.07
     alphabetical
    0.07
    _scal
    0.07
     ув
    0.07
    _types
    0.07
    Activations Density 0.001%

    No Known Activations