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. 74573
    Prev
    Next
    INDEX
    Explanations

    question mark

    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
    .le
    -0.08
    ಚಾರ
    -0.08
     radial
    -0.08
     Moz
    -0.07
     necesariamente
    -0.07
     imposed
    -0.07
    ಾರ
    -0.07
     �
    -0.07
     commodity
    -0.07
     inherently
    -0.07
    POSITIVE LOGITS
     genauer
    0.08
     (?)
    0.08
    鹰
    0.08
     durchführen
    0.08
     Eagle
    0.08
    -ish
    0.08
    (?)
    0.08
     دقیق
    0.08
     혹
    0.08
     gana
    0.08
    Activations Density 0.047%

    No Known Activations