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. 117733
    Prev
    Next
    INDEX
    Explanations

    }

    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
    Dip
    -0.09
    dip
    -0.08
     Dip
    -0.08
    DU
    -0.08
     dip
    -0.07
     ongel
    -0.07
     Kup
    -0.07
    wed
    -0.07
    లా
    -0.07
     roba
    -0.07
    POSITIVE LOGITS
     SPR
    0.08
     ferro
    0.08
     
    0.07
     prevailing
    0.07
     الأ
    0.07
     блю
    0.07
     compre
    0.07
     ط
    0.07
     gar
    0.07
     �
    0.07
    Activations Density 0.052%

    No Known Activations