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. 60886
    Prev
    Next
    INDEX
    Explanations

    sensitivity

    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
    бар
    -0.08
     esports
    -0.08
     komst
    -0.08
     immutable
    -0.08
     socialist
    -0.08
    immutable
    -0.08
     roto
    -0.08
    .bar
    -0.08
    .Bar
    -0.08
     hemorrho
    -0.08
    POSITIVE LOGITS
     rang
    0.10
     inquiries
    0.08
    -datepicker
    0.07
    afil
    0.07
     떨어
    0.07
    ongs
    0.07
    ার্থ
    0.07
     songs
    0.07
     stimuli
    0.07
    ducation
    0.07
    Activations Density 0.003%

    No Known Activations