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. 43201
    Prev
    Next
    INDEX
    Explanations

    0

    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
     indem
    -0.08
    .Year
    -0.07
    dux
    -0.07
    kind
    -0.07
    external
    -0.07
    chron
    -0.07
    .YEAR
    -0.07
    _args
    -0.07
     outer
    -0.07
     updates
    -0.07
    POSITIVE LOGITS
     liggen
    0.09
    ügel
    0.08
    Danh
    0.08
     دقيقة
    0.08
     эҳ
    0.08
     제한
    0.08
     баланд
    0.08
     attend
    0.07
     დონ
    0.07
     assuring
    0.07
    Activations Density 0.009%

    No Known Activations