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. 59281
    Prev
    Next
    INDEX
    Explanations

    ue

    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
     inso
    -0.08
    ною
    -0.08
     effectu
    -0.08
     considerable
    -0.08
     суще
    -0.08
    ിണ
    -0.08
     imme
    -0.08
     menurut
    -0.08
     cleverly
    -0.08
    िंग
    -0.07
    POSITIVE LOGITS
     switch
    0.08
     Emerald
    0.07
     Tari
    0.07
    _delegate
    0.07
    0.07
     Lease
    0.07
     Zet
    0.07
     Bana
    0.07
    風
    0.07
     Keb
    0.07
    Activations Density 0.024%

    No Known Activations