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. 120330
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     Candy
    -0.08
    /plain
    -0.07
    sembl
    -0.07
    nés
    -0.07
     plastique
    -0.07
    /signup
    -0.07
    cona
    -0.07
    Land
    -0.07
    аку
    -0.07
    (Member
    -0.07
    POSITIVE LOGITS
     ஆகிய
    0.08
     �
    0.08
     bajos
    0.07
     等
    0.07
    ਿ
    0.07
     Enum
    0.07
    fir
    0.07
     Etc
    0.07
     午
    0.07
    等等
    0.07
    Activations Density 0.047%

    No Known Activations