Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29955
    Prev
    Next
    INDEX
    Explanations

    reciprocity

    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
     ulang
    -0.08
     overw
    -0.07
    CUS
    -0.07
    -rays
    -0.07
     superbe
    -0.07
    /show
    -0.07
     eruption
    -0.07
    lict
    -0.07
     Eure
    -0.07
     탈
    -0.07
    POSITIVE LOGITS
     recipro
    0.11
     Reciprocity
    0.09
     reciproc
    0.09
     reciprocal
    0.08
     mú
    0.08
     resentment
    0.08
     plenamente
    0.08
     Recipro
    0.07
     निभ
    0.07
    .symmetric
    0.07
    Activations Density 0.008%

    No Known Activations