© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48559
    Prev
    Next
    INDEX
    Explanations

    V

    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
     vô
    -0.09
     gaa
    -0.09
     Nas
    -0.08
     george
    -0.08
    rao
    -0.08
     tôi
    -0.08
     Ethical
    -0.08
     nay
    -0.08
    zaamheid
    -0.08
     prid
    -0.08
    POSITIVE LOGITS
    ielleicht
    0.15
    orauss
    0.14
    orderen
    0.14
    ors
    0.13
    ork
    0.13
    order
    0.12
    ölker
    0.12
    orsch
    0.11
    oll
    0.11
    ög
    0.11
    Activations Density 0.002%

    No Known Activations