© 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. 23-RESID-POST-AA
    6. 6116
    Prev
    Next
    INDEX
    Explanations

    �

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parish
    -0.07
    -0.07
    ்வு
    -0.07
     Tube
    -0.07
     endet
    -0.07
     Plate
    -0.07
     বিদ
    -0.07
     elastic
    -0.07
    না
    -0.07
     viện
    -0.07
    POSITIVE LOGITS
    numer
    0.09
    ол
    0.08
    აწ
    0.08
     practical
    0.08
     sost
    0.08
    олы
    0.08
    െ
    0.08
    完善
    0.07
    ದಲ
    0.07
    են
    0.07
    Activations Density 0.000%

    No Known Activations