© 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. 19-RESID-POST-AA
    11. 103150
    Prev
    Next
    INDEX
    Explanations

    plus or minus sign

    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
     pareil
    -0.10
    <dynamic
    -0.09
     stukje
    -0.08
     tramo
    -0.08
     gånger
    -0.08
     entsprech
    -0.08
    <typeof
    -0.08
     gezet
    -0.08
     små
    -0.08
     stret
    -0.08
    POSITIVE LOGITS
     Imana
    0.08
    ant
    0.08
    atat
    0.08
    owi
    0.08
    -resistant
    0.08
     ones
    0.08
    -a
    0.08
    invert
    0.08
    )^
    0.07
     отсутств
    0.07
    Activations Density 0.011%

    No Known Activations