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. 117576
    Prev
    Next
    INDEX
    Explanations

    .redirect

    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
    वीं
    -0.08
     Öff
    -0.08
     مدار
    -0.08
     fungi
    -0.07
     resonance
    -0.07
     घंट
    -0.07
     trillion
    -0.07
     Reverse
    -0.07
     дверь
    -0.07
    erea
    -0.07
    POSITIVE LOGITS
     periód
    0.09
     zurück
    0.09
     kembali
    0.09
     homepage
    0.08
    สินค้า
    0.08
    (['/
    0.08
    (`/
    0.08
    kehr
    0.08
     `/
    0.08
    куда
    0.08
    Activations Density 0.001%

    No Known Activations