© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6705
    Prev
    Next
    INDEX
    Explanations

    Objet

    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
    ayed
    -0.08
    ermany
    -0.08
     أمير
    -0.08
    AYS
    -0.08
    არკ
    -0.08
     rawa
    -0.08
    ashire
    -0.08
    älfte
    -0.08
    äksi
    -0.08
     Hernández
    -0.08
    POSITIVE LOGITS
    ivos
    0.18
    ivo
    0.17
    IVOS
    0.15
    ివ్
    0.13
    િવ
    0.13
    ീവ്
    0.12
    ividade
    0.12
    ivation
    0.11
    ਿਵ
    0.11
    ivée
    0.11
    Activations Density 0.001%

    No Known Activations