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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 51383
    Prev
    Next
    INDEX
    Explanations

    say "ish" ending

    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
    .Init
    -0.09
    	Init
    -0.09
    IEN
    -0.08
    .Ordinal
    -0.08
    prod
    -0.08
     Ernst
    -0.08
    Texts
    -0.08
     distortion
    -0.08
     yapı
    -0.08
     Staats
    -0.08
    POSITIVE LOGITS
    ish
    0.11
     Quiet
    0.08
    amantha
    0.07
     unravel
    0.07
    ishable
    0.07
    ishna
    0.07
    ishing
    0.07
    хар
    0.07
     harbour
    0.07
     unload
    0.07
    Activations Density 0.000%

    No Known Activations