© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 47232
    Prev
    Next
    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     നടക്കുന്ന
    -0.08
     observed
    -0.07
     interesantes
    -0.07
    Charging
    -0.07
     جلو
    -0.07
     repro
    -0.07
     pog
    -0.07
     monot
    -0.07
     Nachteile
    -0.07
     beob
    -0.07
    POSITIVE LOGITS
     jackpot
    0.10
     धन
    0.09
    幸运
    0.09
     ডাক
    0.09
     lucky
    0.09
     massively
    0.09
     幸运
    0.09
     surpassed
    0.09
     jubil
    0.09
    中了大奖
    0.08
    Activations Density 0.015%

    No Known Activations