© 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. 6232
    Prev
    Next
    INDEX
    Explanations

    say "regards"

    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
    ,false
    -0.10
    -temp
    -0.08
    Only
    -0.08
    Something
    -0.08
    。[
    -0.08
    :G
    -0.08
    :[
    -0.08
    Using
    -0.08
     style
    -0.08
    :F
    -0.08
    POSITIVE LOGITS
     regards
    0.14
    est
    0.13
    esthesia
    0.11
    esthetic
    0.11
    estim
    0.09
    estas
    0.09
     greetings
    0.08
    esteld
    0.08
    estic
    0.08
     Regards
    0.08
    Activations Density 0.001%

    No Known Activations