© 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. 51100
    Prev
    Next
    INDEX
    Explanations

    im

    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
    ️⃣
    -0.08
    irira
    -0.08
    itse
    -0.08
    emeester
    -0.08
     oku
    -0.08
    ième
    -0.08
    ીમાં
    -0.08
    owym
    -0.07
    ismiss
    -0.07
    _Image
    -0.07
    POSITIVE LOGITS
    provement
    0.26
    provements
    0.23
    proved
    0.22
    mun
    0.20
    aging
    0.19
    paired
    0.18
    perfect
    0.18
    proper
    0.18
    munity
    0.18
    prove
    0.17
    Activations Density 0.004%

    No Known Activations