© 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. 96948
    Prev
    Next
    INDEX
    Explanations

    çe

    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
    iyası
    -0.10
    iyar
    -0.10
    iky
    -0.10
    yyat
    -0.09
    iy
    -0.09
     jwt
    -0.09
    iyo
    -0.09
    iating
    -0.09
    lığı
    -0.09
    ícios
    -0.08
    POSITIVE LOGITS
    vede
    0.10
    ಂದ
    0.09
    vel
    0.09
    ագ
    0.09
    ved
    0.08
     Tell
    0.08
    ುಕ
    0.07
     Weird
    0.07
     Erwer
    0.07
    ಾ
    0.07
    Activations Density 0.000%

    No Known Activations