© 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. 6044
    Prev
    Next
    INDEX
    Explanations

    O

    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
    >>,↵
    -0.08
    )),↵
    -0.07
     δύ
    -0.07
    ]],↵
    -0.07
    ']),↵
    -0.07
    ]),↵
    -0.07
    _operand
    -0.07
     menys
    -0.07
    ák
    -0.07
    ')),↵
    -0.07
    POSITIVE LOGITS
     outstanding
    0.09
    asikan
    0.08
     மாத
    0.07
    Mic
    0.07
     mẫu
    0.07
     tramp
    0.07
    _EV
    0.07
     repay
    0.07
     cân
    0.07
     mì
    0.07
    Activations Density 0.000%

    No Known Activations