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

    Neuronpedia

    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. 5672
    Prev
    Next
    INDEX
    Explanations

    say "water"

    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
    ationship
    -0.08
    earned
    -0.08
     населения
    -0.07
     nød
    -0.07
    жав
    -0.07
    दे
    -0.07
     environments
    -0.07
    fillment
    -0.07
    -describedby
    -0.07
     arv
    -0.07
    POSITIVE LOGITS
     spray
    0.16
     turquoise
    0.14
     water
    0.14
     foam
    0.13
     breakers
    0.13
     waves
    0.13
     tubig
    0.12
     espuma
    0.12
     પાણી
    0.12
     Foam
    0.11
    Activations Density 0.022%

    No Known Activations