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. 58209
    Prev
    Next
    INDEX
    Explanations

    =

    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
    sar
    -0.08
     suffers
    -0.07
    stood
    -0.07
    टका
    -0.07
    usual
    -0.07
     suffered
    -0.07
    ampler
    -0.07
    女人
    -0.07
    -minus
    -0.07
    руга
    -0.07
    POSITIVE LOGITS
     начиная
    0.12
     أنحاء
    0.09
     ranging
    0.09
     بداية
    0.08
     gamut
    0.08
     hingga
    0.08
     Blink
    0.08
    בס
    0.08
     allant
    0.08
     byg
    0.08
    Activations Density 0.064%

    No Known Activations