© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102368
    Prev
    Next
    INDEX
    Explanations

    log

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itself
    -0.10
    	is
    -0.09
    =is
    -0.09
    右翼
    -0.09
    ='',
    -0.09
    Literal
    -0.09
    )value
    -0.09
    	inline
    -0.08
    ેલું
    -0.08
    =user
    -0.08
    POSITIVE LOGITS
     log
    0.16
    log
    0.15
     лог
    0.13
     लॉ
    0.12
    logen
    0.12
    .log
    0.12
    ログ
    0.12
    лог
    0.12
     Log
    0.12
     লগ
    0.11
    Activations Density 0.002%

    No Known Activations