© 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. 97242
    Prev
    Next
    INDEX
    Explanations

    Пр

    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
    희
    -0.08
    isuus
    -0.08
    ifically
    -0.08
    icides
    -0.08
     mimi
    -0.07
    comings
    -0.07
    ivery
    -0.07
    itos
    -0.07
    isestä
    -0.07
    isex
    -0.07
    POSITIVE LOGITS
     uitstek
    0.10
    ort
    0.09
    horende
    0.09
     Dang
    0.09
    Dang
    0.09
     dangling
    0.09
    valg
    0.08
    val
    0.08
     当
    0.07
    ortut
    0.07
    Activations Density 0.000%

    No Known Activations