© 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. 23-RESID-POST-AA
    11. 6239
    Prev
    Next
    INDEX
    Explanations

    Lithuanian language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obdob
    -0.08
    асць
    -0.08
    arnation
    -0.08
    ération
    -0.08
    iever
    -0.08
    ေလ
    -0.07
    ýle
    -0.07
    ulif
    -0.07
     Ber
    -0.07
    асці
    -0.07
    POSITIVE LOGITS
    inės
    0.20
    inių
    0.18
    inė
    0.18
    iniai
    0.18
    iniu
    0.14
    inis
    0.13
    inio
    0.13
    škai
    0.12
    inius
    0.11
    šku
    0.11
    Activations Density 0.001%

    No Known Activations