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. 54058
    Prev
    Next
    INDEX
    Explanations

    puzzle solving

    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
     pag
    -0.08
    Pag
    -0.07
     lifestyle
    -0.07
    یلی
    -0.07
     pagh
    -0.07
     probable
    -0.07
     reputable
    -0.07
     throttle
    -0.07
     restrict
    -0.07
     restrictions
    -0.07
    POSITIVE LOGITS
     Initially
    0.11
    Initially
    0.10
     initially
    0.10
    _initial
    0.09
     atuais
    0.09
    (initial
    0.09
     બધા
    0.09
     inicialmente
    0.09
     Atualmente
    0.09
     Originally
    0.09
    Activations Density 0.022%

    No Known Activations