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. 111880
    Prev
    Next
    INDEX
    Explanations

    set theory

    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
    	tc
    -0.08
    -0.07
    	head
    -0.07
     compensated
    -0.07
    identi
    -0.07
    olid
    -0.07
    inol
    -0.07
     onto
    -0.07
    rọ
    -0.07
     indispens
    -0.07
    POSITIVE LOGITS
    _mgr
    0.08
     هند
    0.08
    <App
    0.07
     Yangon
    0.07
    ogra
    0.07
     coast
    0.07
    arau
    0.07
    _ar
    0.07
    AR
    0.07
    Cru
    0.07
    Activations Density 0.000%

    No Known Activations