© 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. 97247
    Prev
    Next
    INDEX
    Explanations

    Ин

    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
    core
    -0.09
    cff
    -0.08
    (core
    -0.08
    	core
    -0.08
    _Core
    -0.08
    er
    -0.08
    ters
    -0.08
    oje
    -0.07
    cid
    -0.07
    cs
    -0.07
    POSITIVE LOGITS
    структ
    0.11
    жен
    0.10
    struct
    0.10
    žen
    0.10
    struction
    0.09
    жь
    0.09
    -charge
    0.09
    pect
    0.09
    ਜ਼
    0.09
    STRUCTOR
    0.09
    Activations Density 0.005%

    No Known Activations