© 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. 7-RESID-POST-AA
    11. 1492
    Prev
    Next
    INDEX
    Explanations

    network ports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diário
    -0.09
    ర్మ
    -0.09
     mam
    -0.08
     gabinete
    -0.08
    脱
    -0.08
     магазин
    -0.08
    ్క
    -0.08
     energético
    -0.08
     색
    -0.08
    campo
    -0.08
    POSITIVE LOGITS
     vessels
    0.09
     vessel
    0.08
    ptr
    0.07
    porcion
    0.07
    ethe
    0.07
     Vessel
    0.07
    950
    0.07
    _ag
    0.07
    urtles
    0.07
    ilter
    0.07
    Activations Density 0.000%

    No Known Activations