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. 78389
    Prev
    Next
    INDEX
    Explanations

    bear

    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
    trans
    -0.07
     Soc
    -0.07
    ký
    -0.07
    afs
    -0.07
     radical
    -0.07
    ivr
    -0.07
    十二
    -0.07
    rd
    -0.07
     donn
    -0.07
    igot
    -0.07
    POSITIVE LOGITS
     Zimmer
    0.09
    beitet
    0.08
     Patri
    0.08
    ු
    0.07
     Oral
    0.07
    Pun
    0.07
    �
    0.07
    侣
    0.07
    否
    0.07
    beitung
    0.07
    Activations Density 0.016%

    No Known Activations