© 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. 96713
    Prev
    Next
    INDEX
    Explanations

    say "rav"

    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
     ಸಂದ
    -0.09
     message
    -0.08
     ACTION
    -0.08
    	message
    -0.08
     equipos
    -0.07
    ודה
    -0.07
    	event
    -0.07
    .message
    -0.07
    _ACTION
    -0.07
    타
    -0.07
    POSITIVE LOGITS
    rav
    0.09
     yad
    0.09
     cheeks
    0.08
    ाहरण
    0.08
    four
    0.08
     meer
    0.08
     rah
    0.08
    ając
    0.08
    arel
    0.08
    ū
    0.08
    Activations Density 0.000%

    No Known Activations