© 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. 5802
    Prev
    Next
    INDEX
    Explanations

    say "backs"

    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
    iting
    -0.10
    YTE
    -0.10
    ITING
    -0.09
    젠
    -0.09
    IGNED
    -0.09
     tsy
    -0.08
    itating
    -0.08
    iating
    -0.08
    ate
    -0.08
    štu
    -0.08
    POSITIVE LOGITS
    backs
    0.21
    back
    0.15
    falls
    0.11
    ness
    0.11
    BACK
    0.10
     drawbacks
    0.10
    points
    0.10
     drawback
    0.09
     disadvantages
    0.09
    offs
    0.09
    Activations Density 0.001%

    No Known Activations