© 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. 91414
    Prev
    Next
    INDEX
    Explanations

    future tense

    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
     rendre
    -0.08
     year
    -0.08
    üb
    -0.07
    ają
    -0.07
     streamline
    -0.07
     акку
    -0.07
     bie
    -0.07
     straighten
    -0.07
     vivement
    -0.07
     fles
    -0.07
    POSITIVE LOGITS
    深爱
    0.09
     forever
    0.09
     любовь
    0.08
    Forever
    0.08
     mourning
    0.08
     الحب
    0.08
    Leader
    0.08
    heem
    0.07
     daughters
    0.07
     सैनिक
    0.07
    Activations Density 0.030%

    No Known Activations