© 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. 96966
    Prev
    Next
    INDEX
    Explanations

    Н

    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
     querendo
    -0.09
     souhaitez
    -0.09
    忘
    -0.08
    كون
    -0.08
    abled
    -0.08
     ukuq
    -0.08
    -sp
    -0.08
    -null
    -0.08
    forgot
    -0.08
     spontane
    -0.08
    POSITIVE LOGITS
    ー
    0.09
    и
    0.08
    Så
    0.08
     gg
    0.08
    И
    0.08
     నుండి
    0.08
    ЕТ
    0.08
    ельзя
    0.08
     Så
    0.07
    ич
    0.07
    Activations Density 0.001%

    No Known Activations