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. 76388
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning

    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
     Доб
    -0.08
    WG
    -0.08
     Radios
    -0.08
     eid
    -0.08
     прош
    -0.07
    账
    -0.07
    Radar
    -0.07
    ದರ
    -0.07
    ddit
    -0.07
    حل
    -0.07
    POSITIVE LOGITS
    (J
    0.08
    und
    0.08
     ј
    0.08
    (j
    0.08
     habido
    0.08
     paj
    0.08
    此同时
    0.07
     Verona
    0.07
    _num
    0.07
    _ALIGNMENT
    0.07
    Activations Density 0.280%

    No Known Activations