© 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. 11-RESID-POST-AA
    11. 29606
    Prev
    Next
    INDEX
    Explanations

    len

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anes
    -0.09
    ong
    -0.08
     tough
    -0.08
    란
    -0.07
    Bn
    -0.07
     baixa
    -0.07
     easy
    -0.07
     Вер
    -0.07
    Ips
    -0.07
     vär
    -0.07
    POSITIVE LOGITS
    Psi
    0.08
    �
    0.08
     Maya
    0.08
    突
    0.08
    'r
    0.08
     dismant
    0.07
     Mendes
    0.07
     vitam
    0.07
    凯
    0.07
     milieu
    0.07
    Activations Density 0.013%

    No Known Activations