© 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. 6198
    Prev
    Next
    INDEX
    Explanations

    hun

    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
     Lord
    -0.08
     enriching
    -0.08
    ायण
    -0.08
     opent
    -0.07
     LORD
    -0.07
    ılığı
    -0.07
     Leuven
    -0.07
     olie
    -0.07
    En
    -0.07
    OY
    -0.07
    POSITIVE LOGITS
    nego
    0.10
    nych
    0.10
    na
    0.10
    ched
    0.10
    gr
    0.09
    ny
    0.09
    ney
    0.09
    neys
    0.09
    zas
    0.08
    nale
    0.08
    Activations Density 0.001%

    No Known Activations