© 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. 51190
    Prev
    Next
    INDEX
    Explanations

    Kelly

    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
    loxacin
    -0.08
    azzjoni
    -0.08
    ציות
    -0.08
    იტ
    -0.08
    тә
    -0.08
    ্যাট
    -0.08
    τός
    -0.08
    ॥
    -0.07
    aten
    -0.07
     bilong
    -0.07
    POSITIVE LOGITS
    Kelly
    0.11
     Kelly
    0.10
    entesque
    0.09
    ียด
    0.09
    WAYS
    0.09
    меш
    0.09
     Width
    0.08
    CEL
    0.08
    Kel
    0.08
    Width
    0.08
    Activations Density 0.036%

    No Known Activations