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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12047
    Prev
    Next
    INDEX
    Explanations

    wet surfaces

    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
     juggling
    -0.08
     إلي
    -0.07
     Desta
    -0.07
    ി
    -0.07
    നായ
    -0.07
    ജന
    -0.07
    aita
    -0.07
    quared
    -0.07
     النجاح
    -0.07
    -president
    -0.07
    POSITIVE LOGITS
     поверхность
    0.12
     backside
    0.11
     exterior
    0.10
    _inside
    0.10
     Covered
    0.09
     underside
    0.09
     inside
    0.09
     Exterior
    0.09
    Exterior
    0.09
     поверхности
    0.09
    Activations Density 0.012%

    No Known Activations