Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54458
    Prev
    Next
    INDEX
    Explanations

    of

    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
     grá
    -0.07
     estrella
    -0.07
     потом
    -0.07
    Lister
    -0.07
    attern
    -0.07
    ווה
    -0.07
    ייער
    -0.07
    +a
    -0.07
     खरी
    -0.07
    &_
    -0.07
    POSITIVE LOGITS
     thro
    0.09
     هفته
    0.09
    しゃ
    0.08
     конц
    0.08
     হয়
    0.08
     Buddh
    0.08
     Rem
    0.08
    alb
    0.08
     интерв
    0.08
     tort
    0.07
    Activations Density 0.033%

    No Known Activations