© 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. 6082
    Prev
    Next
    INDEX
    Explanations

    spr

    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
     technically
    -0.08
    kaŭ
    -0.08
    amakuru
    -0.08
     sip
    -0.08
     buka
    -0.08
     كوب
    -0.07
    bekiston
    -0.07
    技术
    -0.07
    (to
    -0.07
    JAVA
    -0.07
    POSITIVE LOGITS
    ucing
    0.12
    uced
    0.11
    yly
    0.11
    y
    0.10
    ightly
    0.10
    uces
    0.10
    y's
    0.09
    inkles
    0.09
    ained
    0.09
    inter
    0.09
    Activations Density 0.002%

    No Known Activations