© 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. 91286
    Prev
    Next
    INDEX
    Explanations

    letter

    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
     earm
    -0.09
     imyaka
    -0.08
    <?>
    -0.08
    فی
    -0.08
    назнач
    -0.08
     aantal
    -0.08
    otos
    -0.08
     calle
    -0.08
     chandelier
    -0.08
     نائب
    -0.07
    POSITIVE LOGITS
     vowel
    0.13
     अक्ष
    0.12
     spelling
    0.12
     vowels
    0.11
    Letters
    0.11
     letters
    0.11
    letters
    0.10
    -letter
    0.10
     letter
    0.10
    (letter
    0.10
    Activations Density 0.030%

    No Known Activations