© 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 EvalsExportsAPI 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. 50292
    Prev
    Next
    INDEX
    Explanations

    کن

    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
     effected
    -0.09
    -0.08
    (CH
    -0.08
     наиболее
    -0.08
    el
    -0.07
    ocular
    -0.07
     Grind
    -0.07
     Fe
    -0.07
     outset
    -0.07
    ocoder
    -0.07
    POSITIVE LOGITS
    ترل
    0.08
    .performance
    0.08
    ilia
    0.07
     ώστε
    0.07
    ման
    0.07
    ு
    0.07
    hairt
    0.07
     심
    0.07
    ترول
    0.07
    山东
    0.07
    Activations Density 0.000%
    No Known Activations