© 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. 49591
    Prev
    Next
    INDEX
    Explanations

    Namespace

    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
     tarifs
    -0.09
    otherapeut
    -0.09
     //}↵
    -0.08
    tiles
    -0.08
    ografie
    -0.08
    €”
    -0.08
    tiens
    -0.08
    эфф
    -0.08
    �్థ
    -0.08
     //}↵↵
    -0.08
    POSITIVE LOGITS
    Namespace
    0.09
    .Namespace
    0.09
     Marine
    0.08
     Namespace
    0.08
    'M
    0.08
     Mel
    0.08
    .namespace
    0.08
    Path
    0.08
    'm
    0.08
     league
    0.07
    Activations Density 0.001%

    No Known Activations