© 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. 103051
    Prev
    Next
    INDEX
    Explanations

    say "sunlight"

    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
     Valuable
    -0.10
     любую
    -0.09
     (`
    -0.09
     (“
    -0.09
     (=
    -0.08
     Vice
    -0.08
     („
    -0.08
     noodzak
    -0.08
     Operand
    -0.08
     ().
    -0.08
    POSITIVE LOGITS
    -inspired
    0.11
    -
    0.10
    -driven
    0.10
    -gl
    0.09
     elegance
    0.09
     glow
    0.09
     warmth
    0.09
    -focused
    0.09
    znym
    0.09
     chaleureux
    0.09
    Activations Density 0.007%

    No Known Activations