© 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. 19-RESID-POST-AA
    11. 103136
    Prev
    Next
    INDEX
    Explanations

    Coordinates and arrays

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.09
    -centric
    -0.08
    ares
    -0.08
    -intensive
    -0.08
    ------------↵
    -0.07
    -heavy
    -0.07
     reliance
    -0.07
    ursive
    -0.07
    ikler
    -0.07
    arad
    -0.07
    POSITIVE LOGITS
     hivyo
    0.09
    组六
    0.09
     ;;=
    0.08
     zařízení
    0.08
     devam
    0.08
     JSONArray
    0.08
     oba
    0.08
     omogo
    0.08
    τρο
    0.08
     unchanged
    0.08
    Activations Density 0.004%
    No Known Activations