© 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. 102556
    Prev
    Next
    INDEX
    Explanations

    must

    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
    equals
    -0.09
    Trying
    -0.08
    ierra
    -0.08
     equals
    -0.08
    making
    -0.08
    Required
    -0.08
     membutuhkan
    -0.07
    seeing
    -0.07
     Requires
    -0.07
    liner
    -0.07
    POSITIVE LOGITS
     բոլոր
    0.11
     всички
    0.11
     всеми
    0.11
     satisfied
    0.11
     պահպան
    0.11
     όλοι
    0.11
     అన్ని
    0.11
     satisfy
    0.11
     барлық
    0.10
     அனைத்து
    0.10
    Activations Density 0.007%

    No Known Activations