© 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. 11-RESID-POST-AA
    11. 47526
    Prev
    Next
    INDEX
    Explanations

    ab

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oneg
    -0.08
     caution
    -0.07
     concepto
    -0.07
    ащ
    -0.07
    >/
    -0.07
     posit
    -0.07
     candidate
    -0.07
    ctx
    -0.07
    	ctx
    -0.07
    >Select
    -0.07
    POSITIVE LOGITS
     linen
    0.09
     والتن
    0.08
     poem
    0.08
     Monde
    0.08
     Attribution
    0.08
     sorta
    0.08
     chor
    0.08
     ITS
    0.07
    Eso
    0.07
     storyt
    0.07
    Activations Density 0.002%

    No Known Activations