© 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. 96865
    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
    ano
    -0.08
     Cage
    -0.08
     syscall
    -0.08
    babel
    -0.08
     cuisine
    -0.07
    _pass
    -0.07
    cale
    -0.07
    _pas
    -0.07
    Pas
    -0.07
    _cd
    -0.07
    POSITIVE LOGITS
     воз
    0.08
    ริ
    0.08
    ৱ
    0.08
     ret
    0.08
     brachte
    0.08
     ઇ
    0.07
    ستي
    0.07
     reti
    0.07
     Воз
    0.07
     использованием
    0.07
    Activations Density 0.000%

    No Known Activations