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. 3-RESID-POST-AA
    6. 12346
    Prev
    Next
    INDEX
    Explanations

    dreaming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aks
    -0.08
    _ui
    -0.08
     pil
    -0.07
     //{↵
    -0.07
    ীদ
    -0.07
     vague
    -0.07
     mating
    -0.07
     pesc
    -0.07
     EXACT
    -0.07
    Fence
    -0.06
    POSITIVE LOGITS
    امت
    0.09
     KC
    0.08
     SCM
    0.08
     Sime
    0.08
     Sa
    0.08
     opere
    0.08
    oe
    0.08
    228
    0.08
     Ober
    0.07
    数量
    0.07
    Activations Density 0.001%

    No Known Activations