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

    Neuronpedia

    Jacobian LensNEW
    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. 23-RESID-POST-AA
    11. 49555
    Prev
    Next
    INDEX
    Explanations

    Russian job boards

    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
    _tick
    -0.08
     wangu
    -0.07
    _eye
    -0.07
    되고
    -0.07
    released
    -0.07
    _er
    -0.07
     '@/
    -0.07
    tick
    -0.07
     Eye
    -0.07
    reduce
    -0.07
    POSITIVE LOGITS
    	gbc
    0.09
     provoc
    0.08
     праг
    0.08
    putnik
    0.08
    HH
    0.08
    hh
    0.08
    hhh
    0.07
     hled
    0.07
     vít
    0.07
     vinn
    0.07
    Activations Density 0.000%

    No Known Activations