© 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. 3-RESID-POST-AA
    11. 3152
    Prev
    Next
    INDEX
    Explanations

    ranges and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     söyl
    -0.08
    -0.07
     physi
    -0.07
    Bases
    -0.07
     בסיס
    -0.07
    isyen
    -0.07
     bases
    -0.07
    基地
    -0.07
     (!)
    -0.07
    Whilst
    -0.07
    POSITIVE LOGITS
     enj
    0.09
    'im
    0.08
     πρόσ
    0.07
    ’im
    0.07
     عز
    0.07
     beeindruck
    0.07
     Acting
    0.07
     Start
    0.07
     adjectives
    0.07
     �
    0.07
    Activations Density 0.000%
    No Known Activations