© 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. 19-RESID-POST-AA
    11. 18332
    Prev
    Next
    INDEX
    Explanations

    single quote

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assumed
    -0.09
     Each
    -0.09
    	with
    -0.08
     Ass
    -0.08
    _each
    -0.08
    ,but
    -0.08
    .You
    -0.07
    ,e
    -0.07
     Series
    -0.07
    _Collections
    -0.07
    POSITIVE LOGITS
    START
    0.09
    reamble
    0.09
    BEGIN
    0.08
    Inicio
    0.08
    DESCRIPTION
    0.08
    tussen
    0.08
    nington
    0.08
    ഞ
    0.08
    Descripción
    0.08
    tcp
    0.08
    Activations Density 0.000%

    No Known Activations