© 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. 102931
    Prev
    Next
    INDEX
    Explanations

    records

    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
     partenaires
    -0.08
     maturation
    -0.08
     essentielles
    -0.08
    成熟
    -0.08
     vecinos
    -0.08
     essencial
    -0.08
    ภาพ
    -0.08
    交
    -0.08
    edback
    -0.08
    assle
    -0.08
    POSITIVE LOGITS
     Guinness
    0.25
     récord
    0.22
     surpassed
    0.18
     rekord
    0.17
     unglaublic
    0.16
    纪录
    0.16
     record
    0.15
    Longest
    0.15
     surpass
    0.15
     longest
    0.15
    Activations Density 0.069%

    No Known Activations