© 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. 6305
    Prev
    Next
    INDEX
    Explanations

    say 250

    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
    १३
    -0.08
     स्त
    -0.08
    529
    -0.08
     microfiber
    -0.08
     killexams
    -0.08
     Pass
    -0.08
     Passed
    -0.07
    )x
    -0.07
     gypsum
    -0.07
     פע
    -0.07
    POSITIVE LOGITS
    250
    0.10
     vm
    0.07
     Auswahl
    0.07
     selection
    0.07
     oficina
    0.07
    length
    0.07
     sélection
    0.07
    orrection
    0.07
    ોગ
    0.07
    利
    0.07
    Activations Density 0.012%

    No Known Activations