Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43741
    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_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kur
    -0.09
     contempt
    -0.08
    mond
    -0.07
     claim
    -0.07
    עש
    -0.07
     postoji
    -0.07
    URED
    -0.07
     Kur
    -0.07
     clears
    -0.07
     robot
    -0.07
    POSITIVE LOGITS
     Bundesliga
    0.09
    _er
    0.09
     hochwertige
    0.08
     magnificent
    0.07
     Vand
    0.07
     ots
    0.07
     Vou
    0.07
    eto
    0.07
     hin
    0.07
    iana
    0.07
    Activations Density 0.001%

    No Known Activations