© 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. 96804
    Prev
    Next
    INDEX
    Explanations

    sl

    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
    owaniu
    -0.09
     balcony
    -0.08
    ienten
    -0.08
     محمود
    -0.08
    ide
    -0.08
     المغربية
    -0.08
    ungu
    -0.08
     पर्द
    -0.07
     Girona
    -0.07
    Retriever
    -0.07
    POSITIVE LOGITS
    ivered
    0.13
    aw
    0.12
    ivers
    0.10
    ather
    0.10
     awa
    0.10
    aws
    0.10
    athers
    0.09
    awc
    0.09
    AW
    0.09
    aná
    0.09
    Activations Density 0.002%

    No Known Activations