© 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. 91348
    Prev
    Next
    INDEX
    Explanations

    Withholding information

    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
     waste
    -0.08
     poet
    -0.08
     Cyril
    -0.08
    รอง
    -0.07
     parlar
    -0.07
     Lithuan
    -0.07
     animais
    -0.07
    タグ
    -0.07
    astro
    -0.07
     fotograf
    -0.07
    POSITIVE LOGITS
     revealed
    0.09
     పూర్తి
    0.09
     decrypted
    0.09
     माहिती
    0.08
     מידע
    0.08
    encrypted
    0.08
     encrypted
    0.08
    рыв
    0.08
     vollständ
    0.08
     informasi
    0.08
    Activations Density 0.031%

    No Known Activations