© 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. 3-RESID-POST-AA
    11. 12891
    Prev
    Next
    INDEX
    Explanations

    ots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NE
    -0.08
     MOB
    -0.08
     nea
    -0.07
     jargon
    -0.07
     coi
    -0.07
    NE
    -0.07
     alguno
    -0.07
     Cela
    -0.07
    ర్ల
    -0.07
     حال
    -0.07
    POSITIVE LOGITS
    扶
    0.09
     мног
    0.09
    休
    0.08
    疆
    0.08
    익
    0.07
     Consol
    0.07
    풀
    0.07
     Breit
    0.07
     conse
    0.07
     espl
    0.07
    Activations Density 0.009%

    No Known Activations