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. 77250
    Prev
    Next
    INDEX
    Explanations

    Parentheses

    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
    uva
    -0.08
    lias
    -0.08
     Foss
    -0.07
    ves
    -0.07
    format
    -0.07
    라우
    -0.07
    ™
    -0.07
     rall
    -0.07
    point
    -0.07
     marathon
    -0.07
    POSITIVE LOGITS
    447
    0.09
     സുപ
    0.08
     fim
    0.08
    ije
    0.08
    .deep
    0.07
     miscar
    0.07
     enriquec
    0.07
     deemed
    0.07
     profund
    0.07
     entsprechen
    0.07
    Activations Density 0.010%

    No Known Activations