© 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. 11-RESID-POST-AA
    11. 63962
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs

    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
    �
    -0.09
    _requires
    -0.09
     marm
    -0.08
     tonos
    -0.08
    ական
    -0.07
     buried
    -0.07
    _equal
    -0.07
     Marley
    -0.07
     krä
    -0.07
     tələb
    -0.07
    POSITIVE LOGITS
     maximum
    0.13
    限制
    0.13
    Maximum
    0.12
    	max
    0.12
    maximum
    0.12
     সীম
    0.12
     máxim
    0.12
     सीमा
    0.12
    .Maximum
    0.11
     maksimal
    0.11
    Activations Density 0.077%

    No Known Activations