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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 129607
    Prev
    Next
    INDEX
    Explanations

    dissect

    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
    ുന്നത്
    -0.08
    ครับ
    -0.07
     engulf
    -0.07
    /services
    -0.07
    Bis
    -0.07
     bis
    -0.07
    ക്കെ
    -0.07
     കേ
    -0.07
    ക്ക
    -0.07
     bear
    -0.07
    POSITIVE LOGITS
     العدد
    0.08
     previa
    0.08
     المعد
    0.07
     Counts
    0.07
     counts
    0.07
     genealog
    0.07
    হণ
    0.07
    0.07
    0.07
     tys
    0.07
    Activations Density 0.002%

    No Known Activations