© 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. 19-RESID-POST-AA
    11. 102822
    Prev
    Next
    INDEX
    Explanations

    artificial

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    σιμοποι
    -0.09
    φέρον
    -0.08
     நூ
    -0.08
    കട
    -0.08
     reclaim
    -0.07
    саты
    -0.07
     caching
    -0.07
     joita
    -0.07
    剪
    -0.07
    ಬಂಧ
    -0.07
    POSITIVE LOGITS
    general
    0.11
    General
    0.11
     allgeme
    0.11
    _general
    0.10
     general
    0.10
    -general
    0.10
     General
    0.10
     intelligence
    0.10
     Intelligence
    0.09
     GENERAL
    0.09
    Activations Density 0.002%

    No Known Activations