© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 12888
    Prev
    Next
    INDEX
    Explanations

    暗

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wu
    -0.09
     ethic
    -0.08
     Ding
    -0.08
    Nieuw
    -0.07
    ña
    -0.07
    Fort
    -0.07
     vex
    -0.07
    Bare
    -0.07
    ella
    -0.07
     gratuit
    -0.07
    POSITIVE LOGITS
    沈
    0.08
     ACT
    0.08
    လ
    0.08
    र्गत
    0.07
    沉
    0.07
     جو
    0.07
     président
    0.07
    شير
    0.07
     pathological
    0.07
     Bezir
    0.07
    Activations Density 0.002%

    No Known Activations