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. 114121
    Prev
    Next
    INDEX
    Explanations

    Sanskrit terms

    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
    Belg
    -0.09
     Belg
    -0.09
    Brief
    -0.08
    Ба
    -0.08
     belg
    -0.08
     kaka
    -0.08
     kommende
    -0.08
     nant
    -0.08
    localized
    -0.07
    ward
    -0.07
    POSITIVE LOGITS
     क्ष
    0.08
     Repo
    0.08
    ేష
    0.07
     groundwork
    0.07
    =context
    0.07
     fatigue
    0.07
     CL
    0.07
     ક્ષ
    0.07
     infinito
    0.07
     infin
    0.07
    Activations Density 0.008%

    No Known Activations