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. 15-RESID-POST-AA
    6. 19133
    Prev
    Next
    INDEX
    Explanations

    smaller

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _DIRECT
    -0.09
    Direct
    -0.08
     특정
    -0.08
    усь
    -0.08
    usti
    -0.08
    ereo
    -0.08
     Sér
    -0.08
    ង
    -0.08
    -direct
    -0.08
    _direct
    -0.08
    POSITIVE LOGITS
     smaller
    0.17
     Smaller
    0.15
     мень
    0.12
     નાના
    0.12
     nhỏ
    0.12
     छोटे
    0.11
     pequeños
    0.11
     kleinere
    0.11
     کوچ
    0.11
     petits
    0.11
    Activations Density 0.011%

    No Known Activations