© 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. 5810
    Prev
    Next
    INDEX
    Explanations

    individual amounts

    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
     Every
    -0.10
     എല്ലാ
    -0.09
    ufe
    -0.09
     Conditions
    -0.09
    ovolj
    -0.09
     prochaine
    -0.09
     Reasons
    -0.08
    Every
    -0.08
     hangi
    -0.08
     Reason
    -0.08
    POSITIVE LOGITS
     ap
    0.28
    _ap
    0.20
    	ap
    0.19
    ap
    0.19
    Ap
    0.19
    (ap
    0.18
    -ap
    0.18
     chacun
    0.18
     Ap
    0.17
     respectively
    0.16
    Activations Density 0.080%

    No Known Activations