© 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. 47946
    Prev
    Next
    INDEX
    Explanations

    learn

    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
    (us
    -0.08
     rundt
    -0.08
     spirituality
    -0.07
     GAS
    -0.07
     omkring
    -0.07
    halb
    -0.07
    птом
    -0.07
     hierbij
    -0.07
     philosophie
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    #define
    0.08
    Def
    0.08
     گرفتن
    0.08
    def
    0.07
    入
    0.07
     def
    0.07
     入
    0.07
    ouple
    0.07
    nées
    0.07
     nesses
    0.07
    Activations Density 0.006%

    No Known Activations