© 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. 96716
    Prev
    Next
    INDEX
    Explanations

    say iv

    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
     repetir
    -0.09
     Repeat
    -0.09
     arfer
    -0.09
     uair
    -0.08
     xalq
    -0.08
     Pir
    -0.08
     repetition
    -0.08
     Isles
    -0.08
     amser
    -0.08
     хугаца
    -0.08
    POSITIVE LOGITS
    iv
    0.20
    ಿವ
    0.16
    िव
    0.16
    ివ
    0.14
    ிவ
    0.14
    ിവ
    0.14
    ivalent
    0.13
    ிவு
    0.13
    િવ
    0.12
    ಿವು
    0.12
    Activations Density 0.001%

    No Known Activations