© 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. 3-RESID-POST-AA
    11. 2507
    Prev
    Next
    INDEX
    Explanations

    rephrasing

    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
     Gel
    -0.09
     kontro
    -0.08
     bolsa
    -0.08
    Gel
    -0.07
     rapaz
    -0.07
    _backup
    -0.07
    ledger
    -0.07
    -air
    -0.07
    emq
    -0.07
    ellten
    -0.07
    POSITIVE LOGITS
     jargon
    0.08
    PUT
    0.08
     .=
    0.07
     Titanic
    0.07
     thinker
    0.07
     говоря
    0.07
     unanimous
    0.07
     intptr
    0.07
    એક
    0.07
     poner
    0.07
    Activations Density 0.011%

    No Known Activations