© 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. 6007
    Prev
    Next
    INDEX
    Explanations

    I or we

    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
     былі
    -0.13
     byli
    -0.12
     buvo
    -0.12
     są
    -0.12
     são
    -0.11
    noticed
    -0.11
     были
    -0.11
     fikk
    -0.11
     jsou
    -0.11
     recebeu
    -0.11
    POSITIVE LOGITS
     will
    0.20
     should
    0.19
    ’ll
    0.16
     akan
    0.16
     shall
    0.15
     sẽ
    0.15
     produce
    0.15
     need
    0.15
     proceed
    0.15
     write
    0.14
    Activations Density 0.111%

    No Known Activations