© 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. 30140
    Prev
    Next
    INDEX
    Explanations

    host/hosts

    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
    ateful
    -0.08
    endal
    -0.08
    ATES
    -0.08
    	cursor
    -0.08
    ٢٠
    -0.07
     tiên
    -0.07
     الحديد
    -0.07
    OMIC
    -0.07
     �
    -0.07
    adel
    -0.07
    POSITIVE LOGITS
     Εκ
    0.09
     ನೋಡ
    0.08
     Agen
    0.08
     oriented
    0.08
     ಏ
    0.07
    .Per
    0.07
    ult
    0.07
     Vere
    0.07
     exp
    0.07
    ::::
    0.07
    Activations Density 0.001%

    No Known Activations