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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 97358
    Prev
    Next
    INDEX
    Explanations

    pigeon

    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
    jati
    -0.09
    jani
    -0.08
     Abroad
    -0.08
    раструкт
    -0.08
    يل
    -0.08
    ிக்கை
    -0.08
    واقع
    -0.08
    ijiet
    -0.08
    ובות
    -0.08
    ڄ
    -0.08
    POSITIVE LOGITS
     pige
    0.09
    ons
    0.09
    ating
    0.08
    osing
    0.08
    "os
    0.08
     birds
    0.08
     colore
    0.08
    ens
    0.08
    yeurs
    0.08
     fal
    0.08
    Activations Density 0.004%

    No Known Activations