© 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. 68291
    Prev
    Next
    INDEX
    Explanations

    solution verification

    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
    anin
    -0.08
     tuleb
    -0.08
     expedite
    -0.07
     threats
    -0.07
     exacte
    -0.07
     squid
    -0.07
     visite
    -0.07
     несмотря
    -0.07
     redevelopment
    -0.07
     llegue
    -0.07
    POSITIVE LOGITS
     plaus
    0.11
     fits
    0.11
     Fits
    0.10
    符合
    0.10
    fits
    0.10
     plausible
    0.10
     consistency
    0.09
    Fits
    0.09
    ALIGN
    0.08
     enca
    0.08
    Activations Density 0.054%

    No Known Activations