© 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. 48504
    Prev
    Next
    INDEX
    Explanations

    line

    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
    дены
    -0.11
    ציעס
    -0.10
    ცია
    -0.10
    ციის
    -0.09
    ונגען
    -0.09
    ումներ
    -0.09
    ումբ
    -0.09
    ્ઠ
    -0.09
    ENSIONS
    -0.09
    թեր
    -0.09
    POSITIVE LOGITS
    arly
    0.28
    arity
    0.16
    ars
    0.15
    arl
    0.14
    ary
    0.14
    aris
    0.13
    arnya
    0.13
    arth
    0.12
    ar
    0.12
    ární
    0.12
    Activations Density 0.001%

    No Known Activations