© 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. 11-RESID-POST-AA
    11. 29517
    Prev
    Next
    INDEX
    Explanations

    or/no

    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
     softer
    -0.08
    (xpath
    -0.08
     Herz
    -0.08
     hús
    -0.08
    Tas
    -0.08
    .That
    -0.07
    (tr
    -0.07
    ------------------------------------------------------------------------
    -0.07
    .soft
    -0.07
    (['
    -0.07
    POSITIVE LOGITS
    0.08
    ®,
    0.08
    टका
    0.08
     PRIMARY
    0.08
     snee
    0.08
     indique
    0.08
    λεί
    0.08
    otos
    0.07
    SVG
    0.07
     snug
    0.07
    Activations Density 0.010%

    No Known Activations