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. 55959
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     adh
    -0.08
    રૂ
    -0.08
     Firstly
    -0.08
    حم
    -0.08
     castig
    -0.07
     лом
    -0.07
     бара
    -0.07
    gain
    -0.07
     નિ
    -0.07
     ----
    -0.07
    POSITIVE LOGITS
     subdivisions
    0.08
    ค่า
    0.08
    Mé
    0.08
    .gs
    0.08
    Subdivision
    0.08
     imy
    0.08
    /preferences
    0.08
    VERSE
    0.08
    成立
    0.08
     Myth
    0.08
    Activations Density 0.146%

    No Known Activations