© 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. 8157
    Prev
    Next
    INDEX
    Explanations

    aer

    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
     grazing
    -0.08
    横
    -0.07
     выступ
    -0.07
     Evans
    -0.07
     Ah
    -0.07
     TP
    -0.07
     Y
    -0.07
    邀请
    -0.07
     electroly
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     pern
    0.08
    েগ
    0.08
    wissenschaft
    0.08
     Baum
    0.07
    laws
    0.07
    verb
    0.07
     dbg
    0.07
    IMUM
    0.07
    compression
    0.07
     accidents
    0.07
    Activations Density 0.003%

    No Known Activations