Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 52824
    Prev
    Next
    INDEX
    Explanations

    cylinders and math

    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
     recal
    -0.08
     વ્ય
    -0.08
     competitivo
    -0.08
     calibr
    -0.07
     gom
    -0.07
    Bracket
    -0.07
     rtc
    -0.07
    traction
    -0.07
    Gui
    -0.07
    onut
    -0.07
    POSITIVE LOGITS
     cylindrical
    0.10
     πά
    0.09
     cylinders
    0.08
     intermin
    0.08
     longitud
    0.08
     διάρκεια
    0.08
     Length
    0.08
     shafts
    0.08
     неск
    0.08
    高さ
    0.08
    Activations Density 0.032%

    No Known Activations