© 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. 96182
    Prev
    Next
    INDEX
    Explanations

    say "ap or od ending"

    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
    ებ
    -0.08
     monoc
    -0.08
    geben
    -0.07
    მით
    -0.07
    တ္
    -0.07
    μές
    -0.07
    -gener
    -0.07
    ელ
    -0.07
    uint
    -0.07
    ppel
    -0.07
    POSITIVE LOGITS
    apsulation
    0.09
     Purdue
    0.09
     Heap
    0.08
     Temper
    0.08
     Audience
    0.08
     Puffy
    0.08
     Root
    0.08
     Kafka
    0.08
     фут
    0.07
     dueño
    0.07
    Activations Density 0.000%

    No Known Activations