© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 23-RESID-POST-AA
    11. 50256
    Prev
    Next
    INDEX
    Explanations

    say "out" or "from"

    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
     ajustes
    -0.09
    stemming
    -0.09
     stemming
    -0.09
    δη
    -0.09
     adjustments
    -0.08
     włas
    -0.08
     hente
    -0.08
     originating
    -0.08
    κίνη
    -0.08
     retrouvé
    -0.08
    POSITIVE LOGITS
     out
    0.15
     uniformly
    0.12
     מתוך
    0.11
     arbitr
    0.11
    	out
    0.10
     randomly
    0.10
     anywhere
    0.09
     disreg
    0.09
     consecut
    0.09
     아무
    0.09
    Activations Density 0.051%

    No Known Activations