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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98681
    Prev
    Next
    INDEX
    Explanations

    gl

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nevez
    -0.09
     ríg
    -0.08
     taakk
    -0.08
    .exam
    -0.08
     gru
    -0.08
    ydessä
    -0.08
     llen
    -0.08
     fatto
    -0.08
     exam
    -0.08
     stacked
    -0.08
    POSITIVE LOGITS
    immers
    0.12
    int
    0.12
    ints
    0.12
    immer
    0.10
    are
    0.08
    ಿಂ
    0.08
    intig
    0.08
    itched
    0.08
    inten
    0.08
     inm
    0.08
    Activations Density 0.002%

    No Known Activations