© 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. 23-RESID-POST-AA
    11. 48568
    Prev
    Next
    INDEX
    Explanations

    Greetings in different languages

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interestingly
    -0.10
     deshalb
    -0.08
    inyin
    -0.08
    Theta
    -0.08
    Knowing
    -0.07
    Highlight
    -0.07
    IGHL
    -0.07
    Reject
    -0.07
    Así
    -0.07
    Checker
    -0.07
    POSITIVE LOGITS
     Happy
    0.28
     buon
    0.28
     Good
    0.27
     buona
    0.26
     good
    0.25
     bonne
    0.25
     buena
    0.25
    Good
    0.24
     buen
    0.24
     શુભ
    0.23
    Activations Density 0.016%

    No Known Activations