© 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. 48539
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
    త్త
    -0.08
     delights
    -0.08
     Snake
    -0.08
     风
    -0.07
    风
    -0.07
    杯
    -0.07
    ウォ
    -0.07
     الان
    -0.07
     Wszyst
    -0.07
     Cand
    -0.07
    POSITIVE LOGITS
    ક્ટ
    0.08
     utilizado
    0.08
    ktf
    0.08
    ONSE
    0.08
     dramat
    0.07
    efe
    0.07
    _google
    0.07
    	extern
    0.07
    �ે
    0.07
    ুগ
    0.07
    Activations Density 0.000%

    No Known Activations