© 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. 11-RESID-POST-AA
    11. 68241
    Prev
    Next
    INDEX
    Explanations

    Legal sentence structure

    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
     prize
    -0.09
    Prize
    -0.08
    Loot
    -0.08
    Achievement
    -0.08
     achievement
    -0.08
     improb
    -0.07
    loot
    -0.07
    Anal
    -0.07
    lje
    -0.07
     prized
    -0.07
    POSITIVE LOGITS
     untranslated
    0.09
     Insert
    0.09
     frases
    0.09
     correspondente
    0.09
     Chunk
    0.09
     पाठ
    0.08
     sentences
    0.08
     �
    0.08
     משפט
    0.08
     traduction
    0.08
    Activations Density 0.008%

    No Known Activations