© 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. 6420
    Prev
    Next
    INDEX
    Explanations

    прин

    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
    rio
    -0.09
    ில
    -0.08
    nique
    -0.07
     poisoned
    -0.07
     rej
    -0.07
    rypt
    -0.07
    (row
    -0.07
     dias
    -0.07
    ిల
    -0.07
    ielle
    -0.06
    POSITIVE LOGITS
    алеж
    0.13
    уд
    0.11
    цесс
    0.10
    уж
    0.09
    тера
    0.08
    тердің
    0.08
    ың
    0.08
     centr
    0.08
    वाई
    0.08
    DS
    0.08
    Activations Density 0.001%

    No Known Activations