© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 48932
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    -Men
    -0.08
    Epoch
    -0.08
     лат
    -0.08
     olig
    -0.08
    Sol
    -0.08
    Lat
    -0.08
    Men
    -0.08
     latent
    -0.08
    ्ब
    -0.07
     rada
    -0.07
    POSITIVE LOGITS
    identifier
    0.12
    ouvrir
    0.11
    about
    0.11
    indu
    0.10
    atte
    0.10
    emplo
    0.10
    ores
    0.10
    official
    0.10
    endig
    0.10
    êtres
    0.10
    Activations Density 0.001%

    No Known Activations