© 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. 47959
    Prev
    Next
    INDEX
    Explanations

    Joining/attachments

    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
     pik
    -0.08
    �
    -0.08
     малого
    -0.07
    ỏa
    -0.07
     begge
    -0.07
     Kod
    -0.07
    _convert
    -0.07
    re
    -0.07
     स्वर
    -0.07
    -hide
    -0.07
    POSITIVE LOGITS
    oin
    0.15
    مع
    0.13
    OIN
    0.13
    ointi
    0.12
    oi
    0.12
    UNT
    0.11
    unción
    0.11
    ಂಟ
    0.11
    unction
    0.11
    unt
    0.11
    Activations Density 0.001%

    No Known Activations