© 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. 5475
    Prev
    Next
    INDEX
    Explanations

    p

    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
    patrick
    -0.08
    …I
    -0.08
    Philadelphia
    -0.08
    Sunday
    -0.08
    هِ
    -0.08
    Alternatively
    -0.08
    нили
    -0.08
    Mur
    -0.08
    ðir
    -0.08
    Charl
    -0.08
    POSITIVE LOGITS
    avings
    0.08
     ×
    0.08
     x
    0.08
     rq
    0.08
     ·
    0.08
     q
    0.08
    ,q
    0.08
     ਇਸ
    0.07
     qs
    0.07
    ancy
    0.07
    Activations Density 0.001%

    No Known Activations